{
  "id": 2778,
  "title": "How did you do it?",
  "url": "/competitions/acm-sf-chapter-hackathon-big/writeups/zenog-how-did-you-do-it",
  "author_name": "",
  "post_date": "2012-09-30T13:36:16.767Z",
  "votes": 2,
  "comment_count": 2,
  "views": 2987,
  "content": "<p><a href=\"http://www.kaggle.com/c/acm-sf-chapter-hackathon-small/forums/t/2777/how-did-you-do-it/14966\">Same question as in the small dataset forum: How did you do it?</a></p>\r\n<p>I basically used the same approach as for the small dataset, except:</p>\r\n<ul>\r\n<li>there was no category-specific normalization </li><li>kNN computed from similar queries within the same category </li><li>if there were less then 5 items from the kNN, extend the list with most popular items by category, most popular (global) items by query, and globally most popular items\r\n</li></ul>\r\n<p>My last submission was 0.57142.</p>\r\n<p>Instead of cross-validation, I used a 10% split for validation, and sometimes a smaller subset for development. Overfitting was no problem, and the differences between validation results were good predictions for performance on the leaderboard.</p>\r\n<p>The Python script for the final submission took 21.5 minutes to run on my laptop, so no real need for a cluster or cloud computing to tackle this problem ... well of course experiments would still run faster if you had several machines at your fingertips\r\n ...</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>",
  "messages": [
    {
      "id": "14967",
      "postDate": "09/30/2012 13:36:16",
      "content": "<p><a href=\"http://www.kaggle.com/c/acm-sf-chapter-hackathon-small/forums/t/2777/how-did-you-do-it/14966\">Same question as in the small dataset forum: How did you do it?</a></p>\r\n<p>I basically used the same approach as for the small dataset, except:</p>\r\n<ul>\r\n<li>there was no category-specific normalization </li><li>kNN computed from similar queries within the same category </li><li>if there were less then 5 items from the kNN, extend the list with most popular items by category, most popular (global) items by query, and globally most popular items\r\n</li></ul>\r\n<p>My last submission was 0.57142.</p>\r\n<p>Instead of cross-validation, I used a 10% split for validation, and sometimes a smaller subset for development. Overfitting was no problem, and the differences between validation results were good predictions for performance on the leaderboard.</p>\r\n<p>The Python script for the final submission took 21.5 minutes to run on my laptop, so no real need for a cluster or cloud computing to tackle this problem ... well of course experiments would still run faster if you had several machines at your fingertips\r\n ...</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>\r\n<p>&nbsp;</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "14972",
      "postDate": "09/30/2012 19:45:25",
      "content": "<p>How'd you run a kNN? You run it on a term document matrix?</p>\r\n<p>Mine was pretty similar to the benchmark, but I added queries and month to the string to make it :</p>\r\n<p>category-query-month</p>\r\n<p>then I filled in blanks with benchmark.&nbsp; I also tried using week-of-year as an input but the score was worse.</p>",
      "rawMarkdown": "",
      "votes": null
    },
    {
      "id": "14975",
      "postDate": "09/30/2012 20:21:04",
      "content": "<p>I ran kNN on the query strings.</p>",
      "rawMarkdown": "",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 14972,
      "author_name": "barrenwuffet",
      "author_url": "",
      "post_date": "09/30/2012 19:45:25",
      "content": "<p>How'd you run a kNN? You run it on a term document matrix?</p>\r\n<p>Mine was pretty similar to the benchmark, but I added queries and month to the string to make it :</p>\r\n<p>category-query-month</p>\r\n<p>then I filled in blanks with benchmark.&nbsp; I also tried using week-of-year as an input but the score was worse.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 14975,
      "author_name": "zenog15462",
      "author_url": "",
      "post_date": "09/30/2012 20:21:04",
      "content": "<p>I ran kNN on the query strings.</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "14967": "",
    "14972": "",
    "14975": ""
  },
  "source": "existing_discussion",
  "complete": true,
  "competition_id": 3064,
  "competition_slug": "acm-sf-chapter-hackathon-big",
  "team_id": 23924,
  "solution_url": "/competitions/acm-sf-chapter-hackathon-big/writeups/zenog-how-did-you-do-it"
}